© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13973
    Prev
    Next
    INDEX
    Explanations

    references to visual elements and aspects of design in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    file paths and image filenames in HTML markup.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Large
    -0.44
     lourdes
    -0.43
     大型
    -0.42
    大型
    -0.41
    Massive
    -0.40
    Giant
    -0.40
    Huge
    -0.40
    Vidite
    -0.39
    aarrggbb
    -0.38
     heavyweight
    -0.38
    POSITIVE LOGITS
     small
    2.30
     tiny
    2.23
    small
    2.09
     SMALL
    1.98
    Small
    1.96
     smaller
    1.94
     Small
    1.94
    tiny
    1.88
     pequeñas
    1.85
     diminutive
    1.85
    Activations Density 0.852%

    No Known Activations